TL;DR

To download a particular dataset/models, use the nltk.download() function, e.g. if you are looking to download the punkt sentence tokenizer, use:

$ python3
>>> import nltk
>>> nltk.download('punkt')

If you’re unsure of which data/model you need, you can start out with the basic list of data + models with:

>>> import nltk
>>> nltk.download('popular')

It will download a list of “popular” resources, these includes:

<collection id="popular" name="Popular packages">
      <item ref="cmudict" />
      <item ref="gazetteers" />
      <item ref="genesis" />
      <item ref="gutenberg" />
      <item ref="inaugural" />
      <item ref="movie_reviews" />
      <item ref="names" />
      <item ref="shakespeare" />
      <item ref="stopwords" />
      <item ref="treebank" />
      <item ref="twitter_samples" />
      <item ref="omw" />
      <item ref="wordnet" />
      <item ref="wordnet_ic" />
      <item ref="words" />
      <item ref="maxent_ne_chunker" />
      <item ref="punkt" />
      <item ref="snowball_data" />
      <item ref="averaged_perceptron_tagger" />
    </collection>

EDITED

In case anyone is avoiding errors from downloading larger datasets from nltk, from https://stackoverflow.com/a/38135306/610569

$ rm /Users/<your_username>/nltk_data/corpora/panlex_lite.zip
$ rm -r /Users/<your_username>/nltk_data/corpora/panlex_lite
$ python

>>> import nltk
>>> dler = nltk.downloader.Downloader()
>>> dler._update_index()
>>> dler._status_cache['panlex_lite'] = 'installed' # Trick the index to treat panlex_lite as it's already installed.
>>> dler.download('popular')

Updated

From v3.2.5, NLTK has a more informative error message when nltk_data resource is not found, e.g.:

>>> from nltk import word_tokenize
>>> word_tokenize('x')
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/Users/l/alvas/git/nltk/nltk/tokenize/__init__.py", line 128, in word_tokenize
    sentences = [text] if preserve_line else sent_tokenize(text, language)
  File "/Users//alvas/git/nltk/nltk/tokenize/__init__.py", line 94, in sent_tokenize
    tokenizer = load('tokenizers/punkt/{0}.pickle'.format(language))
  File "/Users/alvas/git/nltk/nltk/data.py", line 820, in load
    opened_resource = _open(resource_url)
  File "/Users/alvas/git/nltk/nltk/data.py", line 938, in _open
    return find(path_, path + ['']).open()
  File "/Users/alvas/git/nltk/nltk/data.py", line 659, in find
    raise LookupError(resource_not_found)
LookupError: 
**********************************************************************
  Resource punkt not found.
  Please use the NLTK Downloader to obtain the resource:

  >>> import nltk
  >>> nltk.download('punkt')

  Searched in:
    - '/Users/alvas/nltk_data'
    - '/usr/share/nltk_data'
    - '/usr/local/share/nltk_data'
    - '/usr/lib/nltk_data'
    - '/usr/local/lib/nltk_data'
    - ''
**********************************************************************

Related

• To find nltk_data directory (auto-magically), see https://stackoverflow.com/a/36383314/610569

• To download nltk_data to a different path, see https://stackoverflow.com/a/48634212/610569

• To config nltk_data path (i.e. set a different path for NLTK to find nltk_data), see https://stackoverflow.com/a/22987374/610569